Image Segmentation
Transformers
PyTorch
Safetensors
segformer
Generated from Trainer
document-image-binarization
Instructions to use DiTo97/binarization-segformer-b3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use DiTo97/binarization-segformer-b3 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-segmentation", model="DiTo97/binarization-segformer-b3")# Load model directly from transformers import AutoImageProcessor, SegformerForSemanticSegmentation processor = AutoImageProcessor.from_pretrained("DiTo97/binarization-segformer-b3") model = SegformerForSemanticSegmentation.from_pretrained("DiTo97/binarization-segformer-b3") - Notebooks
- Google Colab
- Kaggle
Updated README.md
Browse files
README.md
CHANGED
|
@@ -26,11 +26,11 @@ It achieves the following results on the evaluation set on DIBCO metrics:
|
|
| 26 |
|
| 27 |
For more information on DIBCO metrics, see the [paper](https://ieeexplore.ieee.org/document/8270159) in which they were introduced.
|
| 28 |
|
| 29 |
-
**Warning:** This model only accepts images with a resolution of 640 due to compute constraints during training.
|
| 30 |
|
| 31 |
## Model description
|
| 32 |
|
| 33 |
-
This model is part of on-going research on pure semantic segmentation models as a formulation of document image binarization.
|
| 34 |
|
| 35 |
## Intended uses & limitations
|
| 36 |
|
|
|
|
| 26 |
|
| 27 |
For more information on DIBCO metrics, see the [paper](https://ieeexplore.ieee.org/document/8270159) in which they were introduced.
|
| 28 |
|
| 29 |
+
**Warning:** This model only accepts images with a resolution of 640 due to compute constraints on Colab free tier during training.
|
| 30 |
|
| 31 |
## Model description
|
| 32 |
|
| 33 |
+
This model is part of on-going research on pure semantic segmentation models as a formulation of document image binarization (DIBCO).
|
| 34 |
|
| 35 |
## Intended uses & limitations
|
| 36 |
|